Share Email Print

Optical Engineering

Multiwindow least-squares approach to the estimation of optical flow with discontinuities
Author(s): Franco Bartolini; Vito Cappellini; Carlo Colombo; Alessandro Mecocci
Format Member Price Non-Member Price
PDF $24.00 $28.00

Paper Abstract

The use of optical flow fields in image sequence analysis allows us to perform motion-based segmentation as well as 3-D reconstruction. Many techniques for optical flow estimation are based on some global or piecewise global smoothness assumption. Other techniques compute the flow field based only on local information. A local algorithm explicitly addressing the problem of evaluating a reliable optical flow field at motion boundaries is presented. Velocity vectors are computed as solutions of a multiwindow least-squares problem; the field is then regularized by a vector median filter. The algorithm is noniterative and nonparametric. Results on both synthetic and real-world sequences are shown; a performance comparison with two well-known techniques demonstrates the effectiveness of the algorithm in terms of noise rejection, motion boundary preservation, and speed.

Paper Details

Date Published: 1 June 1993
PDF: 7 pages
Opt. Eng. 32(6) doi: 10.1117/12.134199
Published in: Optical Engineering Volume 32, Issue 6
Show Author Affiliations
Franco Bartolini, Univ. degli Studi di Firenze (Italy)
Vito Cappellini, Univ. degli Studi di Firenze (Italy)
Carlo Colombo, Scuola Superiore Sant'Anna (Italy)
Alessandro Mecocci, Univ. degli Studi di Siena (Italy)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?